mini-swe-agent 1.17.5__py3-none-any.whl → 2.0.0a1__py3-none-any.whl

minisweagent/config/{extra → benchmarks}/swebench_xml.yaml

@@ -9,7 +9,7 @@ agent:
     <format_example>
     THOUGHT: Your reasoning and analysis here
 
-    <bash_code>your_command_here</bash_code>
+    <mswea_bash_command>your_command_here</mswea_bash_command>
     </format_example>
 
     Failure to follow these rules will cause your response to be rejected.
@@ -23,21 +23,25 @@ agent:
     # Task Instructions
 
     ## Overview
+
     You're a software engineer interacting continuously with a computer by submitting commands.
     You'll be helping implement necessary changes to meet requirements in the PR description.
     Your task is specifically to make changes to non-test files in the current directory in order to fix the issue described in the PR description in a way that is general and consistent with the codebase.
 
-    IMPORTANT: This is an interactive process where you will think and issue ONE command, see its result, then think and issue your next command.
+    <IMPORTANT>This is an interactive process where you will think and issue ONE command, see its result, then think and issue your next command.</IMPORTANT>
 
     For each response:
+
     1. Include a THOUGHT section explaining your reasoning and what you're trying to accomplish
     2. Provide exactly ONE bash command to execute
 
     ## Important Boundaries
+
     - MODIFY: Regular source code files in /testbed (this is the working directory for all your subsequent commands)
     - DO NOT MODIFY: Tests, configuration files (pyproject.toml, setup.cfg, etc.)
 
     ## Recommended Workflow
+
     1. Analyze the codebase by finding and reading relevant files
     2. Create a script to reproduce the issue
     3. Edit the source code to resolve the issue
@@ -45,29 +49,36 @@ agent:
     5. Test edge cases to ensure your fix is robust
 
     ## Command Execution Rules
+
     You are operating in an environment where
+
     1. You write a single command
     2. The system executes that command in a subshell
     3. You see the result
     4. You write your next command
 
     Each response should include:
+
     1. A **THOUGHT** section where you explain your reasoning and plan
     2. A single bash code block with your command
 
-    Format your responses like included within the <format_example> block:
+    Format your responses like demonstrated within the <format_example> block:
 
     <format_example>
     THOUGHT: Here I explain my reasoning process, analysis of the current situation,
     and what I'm trying to accomplish with the command below.
 
-    <bash_code>your_command_here </bash_code></format_example>
+    <mswea_bash_command>your_command_here</mswea_bash_command></format_example>
+    Commands must be specified in a single bash XML tag:
+
+    <mswea_bash_command>your_command_here</mswea_bash_command>
 
     **CRITICAL REQUIREMENTS:**
+
     - Your response SHOULD include a THOUGHT section explaining your reasoning
-    - Your response MUST include EXACTLY ONE bash code block
-    - This bash block MUST contain EXACTLY ONE command (or a set of commands connected with && or ||)
-    - If you include zero or multiple bash blocks, or no command at all, YOUR RESPONSE WILL FAIL
+    - Your response MUST include EXACTLY ONE mswea_bash_command tag
+    - This bash mswea_bash_command MUST contain EXACTLY ONE command (or a set of commands connected with && or ||)
+    - If you include zero or multiple tags, or no command at all, YOUR RESPONSE WILL FAIL
     - Do NOT try to run multiple independent commands in separate blocks in one response
     - Directory or environment variable changes are not persistent. Every action is executed in a new subshell.
     - However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files
@@ -77,7 +88,7 @@ agent:
     <example_response>
     THOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
 
-    <bash_code>ls -la</bash_code>
+    <mswea_bash_command>ls -la</mswea_bash_command>
     </example_response>
 
     Example of an INCORRECT response:
@@ -85,18 +96,18 @@ agent:
     <example_response>
     THOUGHT: I need to examine the codebase and then look at a specific file. I'll run multiple commands to do this.
 
-    <bash_code>ls -la</bash_code>
+    <mswea_bash_command>ls -la</mswea_bash_command>
 
     Now I'll read the file:
 
-    <bash_code>cat file.txt</bash_code>
+    <mswea_bash_command>cat file.txt</mswea_bash_command>
     </example_response>
 
     If you need to run multiple commands, either:
 
     1. Combine them in one block using && or ||
 
-    <bash_code>command1 && command2 || echo "Error occurred"</bash_code>
+    <mswea_bash_command>command1 && command2 || echo "Error occurred"</mswea_bash_command>
 
     2. Wait for the first command to complete, see its output, then issue the next command in your following response.
 
@@ -105,57 +116,64 @@ agent:
     - You have a full Linux shell environment
     - Always use non-interactive flags (-y, -f) for commands
     - Avoid interactive tools like vi, nano, or any that require user input
-    - If a command isn't available, you can install it
-
-    ## Useful Command Examples
-
-    ### Create a new file:
-
-    <bash_code>cat <<'EOF' > newfile.py
-    import numpy as np
-    hello = "world"
-    print(hello)
-    EOF</bash_code>
-
-    ### Edit files with sed:
+    - You can use bash commands or invoke any tool that is available in the environment
+    - You can also create new tools or scripts to help you with the task
+    - If a tool isn't available, you can also install it
 
-    Replace all occurrences
-
-    <bash_code>sed -i 's/old_string/new_string/g' filename.py</bash_code>
-
-    Replace only first occurrence
-
-    <bash_code>sed -i 's/old_string/new_string/' filename.py</bash_code>
-
-    Replace first occurrence on line 1
-
-    <bash_code>sed -i '1s/old_string/new_string/' filename.py</bash_code>
+    ## Submission
 
-    Replace all occurrences in lines 1-10
+    When you've completed your work, you MUST submit your changes as a git patch.
+    Follow these steps IN ORDER, with SEPARATE commands:
 
-    <bash_code>sed -i '1,10s/old_string/new_string/g' filename.py</bash_code>
+    Step 1: Create the patch file
+    Run `git diff -- path/to/file1 path/to/file2 > patch.txt` listing only the source files you modified.
+    Do NOT commit your changes.
 
-    ### View file content:
+    <IMPORTANT>
+    The patch must only contain changes to the specific source files you modified to fix the issue.
+    Do not submit file creations or changes to any of the following files:
 
-    View specific lines with numbers
+    - test and reproduction files
+    - helper scripts, tests, or tools that you created
+    - installation, build, packaging, configuration, or setup scripts unless they are directly part of the issue you were fixing (you can assume that the environment is already set up for your client)
+    - binary or compiled files
+    </IMPORTANT>
 
-    <bash_code> nl -ba filename.py | sed -n '10,20p'</bash_code>
+    Step 2: Verify your patch
+    Inspect patch.txt to confirm it only contains your intended changes and headers show `--- a/` and `+++ b/` paths.
 
-    Any other command you want to run
+    Step 3: Submit (EXACT command required)
+    You MUST use this EXACT command to submit:
 
-    <bash_code>anything</bash_code>
+    <mswea_bash_command>echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT && cat patch.txt</mswea_bash_command>
 
-    ## Submission
+    If the command fails (nonzero exit status), it will not submit.
 
-    When you've completed your work (reading, editing, testing), and cannot make further progress
-    issue exactly the following command:
+    <CRITICAL>
+    - Creating/viewing the patch and submitting it MUST be separate commands (not combined with &&).
+    - If you modify patch.txt after verifying, you SHOULD verify again before submitting.
+    - You CANNOT continue working (reading, editing, testing) in any way on this task after submitting.
+    </CRITICAL>
+    </instructions>
+  step_limit: 250
+  cost_limit: 3.
 
-    <bash_code>echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT && git add -A && git diff --cached</bash_code>
+environment:
+  cwd: "/testbed"
+  timeout: 60
+  env:
+    PAGER: cat
+    MANPAGER: cat
+    LESS: -R
+    PIP_PROGRESS_BAR: 'off'
+    TQDM_DISABLE: '1'
+  environment_class: docker
 
-    This command will submit your work.
-    You cannot continue working (reading, editing, testing) in any way on this task after submitting.
-    </instructions>
-  action_observation_template: |
+model:
+  observation_template: |
+    {% if output.exception_info -%}
+    <exception>{{output.exception_info}}</exception>
+    {% endif -%}
     <returncode>{{output.returncode}}</returncode>
     {% if output.output | length < 10000 -%}
     <output>
@@ -180,36 +198,21 @@ agent:
     {{ output.output[-5000:] }}
     </output_tail>
     {%- endif -%}
+  action_regex: <mswea_bash_command>(.*?)</mswea_bash_command>
   format_error_template: |
-    Please always provide EXACTLY ONE action in the `<bash_code>` block, found {{actions|length}} actions.
+    Please always provide EXACTLY ONE action in the `<mswea_bash_command>` block, found {{actions|length}} actions.
 
-    Please format your action in a `<bash_code>` block as shown in <response_example>.
+    Please format your action in a `<mswea_bash_command>` block as shown in <response_example>.
 
     <response_example>
     Here are some thoughts about why you want to perform the action.
 
-    <bash_code>ls -la</bash_code>
+    <mswea_bash_command>ls -la</mswea_bash_command>
     </response_example>
 
     If you have completed your assignment, please consult the first message about how to
     submit your solution (you will not be able to continue working on this task after that).
-  step_limit: 250
-  cost_limit: 3.
-  action_regex: <bash_code>(.*?)</bash_code>
-
-environment:
-  cwd: "/testbed"
-  timeout: 60
-  env:
-    PAGER: cat
-    MANPAGER: cat
-    LESS: -R
-    PIP_PROGRESS_BAR: 'off'
-    TQDM_DISABLE: '1'
-  environment_class: docker
-
-model:
   model_name: "minimax/minimax-m2"
   model_class: openrouter
   model_kwargs:
-    temperature: 0.0
+    temperature: 0.0

minisweagent/config/default.yaml

@@ -9,7 +9,7 @@ agent:
     <format_example>
     Your reasoning and analysis here. Explain why you want to perform the action.
 
-    ```bash
+    ```mswea_bash_command
     your_command_here
     ```
     </format_example>
@@ -50,7 +50,7 @@ agent:
     <example_response>
     THOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
 
-    ```bash
+    ```mswea_bash_command
     ls -la
     ```
     </example_response>
@@ -59,7 +59,7 @@ agent:
 
     ### Create a new file:
 
-    ```bash
+    ```mswea_bash_command
     cat <<'EOF' > newfile.py
     import numpy as np
     hello = "world"
@@ -75,7 +75,7 @@ agent:
     </important>
     {%- endif -%}
 
-    ```bash
+    ```mswea_bash_command
     # Replace all occurrences
     sed -i 's/old_string/new_string/g' filename.py
 
@@ -91,17 +91,30 @@ agent:
 
     ### View file content:
 
-    ```bash
+    ```mswea_bash_command
     # View specific lines with numbers
     nl -ba filename.py | sed -n '10,20p'
     ```
 
     ### Any other command you want to run
 
-    ```bash
+    ```mswea_bash_command
     anything
     ```
-  action_observation_template: |
+  step_limit: 0
+  cost_limit: 0.
+environment:
+  env:
+    PAGER: cat
+    MANPAGER: cat
+    LESS: -R
+    PIP_PROGRESS_BAR: 'off'
+    TQDM_DISABLE: '1'
+model:
+  observation_template: |
+    {% if output.exception_info -%}
+    <exception>{{output.exception_info}}</exception>
+    {% endif -%}
     <returncode>{{output.returncode}}</returncode>
     {% if output.output | length < 10000 -%}
     <output>
@@ -126,6 +139,8 @@ agent:
     {{ output.output[-5000:] }}
     </output_tail>
     {%- endif -%}
+  model_kwargs:
+    drop_params: true
   format_error_template: |
     Please always provide EXACTLY ONE action in triple backticks, found {{actions|length}} actions.
     If you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`
@@ -135,22 +150,10 @@ agent:
     <response_example>
     Here are some thoughts about why you want to perform the action.
 
-    ```bash
+    ```mswea_bash_command
     <action>
     ```
     </response_example>
 
     Note: In rare cases, if you need to reference a similar format in your command, you might have
-    to proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```bash.
-  step_limit: 0.
-  cost_limit: 0.
-environment:
-  env:
-    PAGER: cat
-    MANPAGER: cat
-    LESS: -R
-    PIP_PROGRESS_BAR: 'off'
-    TQDM_DISABLE: '1'
-model:
-  model_kwargs:
-    drop_params: true
+    to proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```mswea_bash_command.

minisweagent/config/inspector.tcss

@@ -0,0 +1,42 @@
+/* Trajectory Inspector Styles */
+
+#main {
+    height: 1fr;
+    overflow: hidden;
+}
+
+VerticalScroll {
+    height: 1fr;
+}
+
+#content {
+    height: auto;
+    padding: 1;
+}
+
+.message-container {
+    height: auto;
+    margin-bottom: 1;
+    padding: 0 1;
+}
+
+.message-header {
+    background: $accent;
+    color: $text;
+    padding: 0 1;
+    text-style: bold;
+}
+
+.message-content {
+    height: auto;
+    padding: 1;
+    background: $surface;
+}
+
+Header {
+    dock: top;
+}
+
+Footer {
+    dock: bottom;
+}

minisweagent/config/mini.yaml

@@ -1,20 +1,6 @@
 agent:
   system_template: |
     You are a helpful assistant that can interact with a computer.
-
-    Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).
-    Include a THOUGHT section before your command where you explain your reasoning process.
-    Format your response as shown in <format_example>.
-
-    <format_example>
-    Your reasoning and analysis here. Explain why you want to perform the action.
-
-    ```bash
-    your_command_here
-    ```
-    </format_example>
-
-    Failure to follow these rules will cause your response to be rejected.
   instance_template: |
     Please solve this issue: {{task}}
 
@@ -32,29 +18,40 @@ agent:
     6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.
        Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>
 
-    ## Important Rules
+    ## Command Execution Rules
 
-    1. Every response must contain exactly one action
-    2. The action must be enclosed in triple backticks
-    3. Directory or environment variable changes are not persistent. Every action is executed in a new subshell.
-       However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files
+    You are operating in an environment where
 
-    <system_information>
-    {{system}} {{release}} {{version}} {{machine}}
-    </system_information>
+    1. You issue at least one command
+    2. The system executes the command(s) in a subshell
+    3. You see the result(s)
+    4. You write your next command(s)
 
-    ## Formatting your response
+    Each response should include:
 
-    Here is an example of a correct response:
+    1. **Reasoning text** where you explain your analysis and plan
+    2. At least one tool call with your command
 
+    **CRITICAL REQUIREMENTS:**
+
+    - Your response SHOULD include reasoning text explaining what you're doing
+    - Your response MUST include AT LEAST ONE bash tool call
+    - Directory or environment variable changes are not persistent. Every action is executed in a new subshell.
+    - However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files
+    - Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.
+      Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>
+
+    Example of a CORRECT response:
     <example_response>
-    THOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
+    I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
 
-    ```bash
-    ls -la
-    ```
+    [Makes bash tool call with {"command": "ls -la"} as arguments]
     </example_response>
 
+    <system_information>
+    {{system}} {{release}} {{version}} {{machine}}
+    </system_information>
+
     ## Useful command examples
 
     ### Create a new file:
@@ -101,48 +98,7 @@ agent:
     ```bash
     anything
     ```
-  action_observation_template: |
-    <returncode>{{output.returncode}}</returncode>
-    {% if output.output | length < 10000 -%}
-    <output>
-    {{ output.output -}}
-    </output>
-    {%- else -%}
-    <warning>
-    The output of your last command was too long.
-    Please try a different command that produces less output.
-    If you're looking at a file you can try use head, tail or sed to view a smaller number of lines selectively.
-    If you're using grep or find and it produced too much output, you can use a more selective search pattern.
-    If you really need to see something from the full command's output, you can redirect output to a file and then search in that file.
-    </warning>
-    {%- set elided_chars = output.output | length - 10000 -%}
-    <output_head>
-    {{ output.output[:5000] }}
-    </output_head>
-    <elided_chars>
-    {{ elided_chars }} characters elided
-    </elided_chars>
-    <output_tail>
-    {{ output.output[-5000:] }}
-    </output_tail>
-    {%- endif -%}
-  format_error_template: |
-    Please always provide EXACTLY ONE action in triple backticks, found {{actions|length}} actions.
-    If you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`
-    without any other command.
-    Else, please format your response exactly as follows:
-
-    <response_example>
-    Here are some thoughts about why you want to perform the action.
-
-    ```bash
-    <action>
-    ```
-    </response_example>
-
-    Note: In rare cases, if you need to reference a similar format in your command, you might have
-    to proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```bash.
-  step_limit: 0.
+  step_limit: 0
   cost_limit: 3.
   mode: confirm
 environment:
@@ -153,5 +109,31 @@ environment:
     PIP_PROGRESS_BAR: 'off'
     TQDM_DISABLE: '1'
 model:
+  observation_template: |
+    {%- if output.output | length < 10000 -%}
+    {
+      "returncode": {{ output.returncode }},
+      "output": {{ output.output | tojson }}
+      {%- if output.exception_info %}, "exception_info": {{ output.exception_info | tojson }}{% endif %}
+    }
+    {%- else -%}
+    {
+      "returncode": {{ output.returncode }},
+      "output_head": {{ output.output[:5000] | tojson }},
+      "output_tail": {{ output.output[-5000:] | tojson }},
+      "elided_chars": {{ output.output | length - 10000 }},
+      "warning": "Output too long."
+      {%- if output.exception_info %}, "exception_info": {{ output.exception_info | tojson }}{% endif %}
+    }
+    {%- endif -%}
+  format_error_template: |
+    Tool call error. Every response needs to use the 'bash' tool at least once to execute commands.
+
+    Call the bash tool with your command as the argument:
+    - Tool: bash
+    - Arguments: {"command": "your_command_here"}
+
+    If you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`
+    without any other command.
   model_kwargs:
-    drop_params: true
+    drop_params: true